US 20040260739 A1 Abstract Presented herein is a system and apparatus for accelerating arithmetic decoding of encoded data. In one embodiment, there is presented a symbol interpreter for decoding CABAC coded data. The symbol interpreter comprises a first memory, a CABAC decoding loop, and a syntax assembler. The first memory receives a bitstream comprising the CABAC coded data at a channel rate. The CABAC decoding loop decodes the CABAC symbols at the channel rate, and comprises an arithmetic decoder for generating binary symbols from the CABAC coded data at the channel rate. The syntax assembler decodes the binary symbols at a consumption rate.
Claims(15) 1. A method for decoding context adaptive binary arithmetic coded data, said method comprising:
receiving a bitstream comprising the context adaptive binary arithmetic coded data at a channel rate; decoding the context adaptive binary arithmetic coded data at the channel rate, wherein decoding the context adaptive binary arithmetic coded data at the channel rate comprises generating binary symbols from the context adaptive binary arithmetic coded data at the channel rate; and decoding the binary symbols at a consumption rate. 2. The method of generating syntax elements from the binary symbols at the channel rate; selecting context table entries for decoding a portion of the binary symbols on the basis of a portion of the syntax elements, the portion of the syntax elements corresponding to another portion of the binary symbols, the another portion of the binary symbols preceding the portion of the binary symbols. 3. The method of generating syntax elements from the binary symbols at the consumption rate. 4. The method of writing the binary symbols to a memory. 5. The method of requesting the binary symbols from the memory at the consumption rate. 6. A decoder for decoding context adaptive binary coded data, said decoder comprising:
a first memory for receiving at a channel rate, a bitstream comprising the context adaptive binary coded data; a context adaptive binary arithmetic coded data decoding loop for decoding the context adaptive binary arithmetic coded data at the channel rate, the context adaptive binary arithmetic coded data decoding loop comprising an arithmetic decoder for generating binary symbols from the context adaptive binary arithmetic coded data at the channel rate; and a syntax assembler for decoding the binary symbols at a consumption rate, thereby generating syntax elements. 7. The decoder of another syntax assembler for generating syntax elements from the binary symbols at the channel rate; a selector for selecting context table entries for decoding a portion of the binary symbols on the basis of a portion of the syntax elements, the portion of the syntax elements corresponding to another portion of the binary symbols, the another portion of the binary symbols preceding the portion of the binary symbols. 8. The decoder of another memory for storing the binary symbols. 9. The decoder of 10. The decoder of 11. A decoder for decoding context adaptive binary arithmetic coded data, said decoder comprising:
a first memory for receiving at a channel rate, a bitstream comprising the context adaptive binary arithmetic coded data; a context adaptive binary arithmetic coded data decoding loop operably coupled to the first memory to decode the context adaptive binary arithmetic coded data at the channel rate, the context adaptive binary arithmetic coded data decoding loop further comprising an arithmetic decoder operably coupled to the first memory to generate binary symbols from the context adaptive binary arithmetic coded data at the channel rate; and a syntax assembler operably coupled to the arithmetic decoder to decode the binary symbols at a consumption rate, thereby generating syntax elements. 12. The decoder of another syntax assembler operably coupled to the arithmetic decoder to generate syntax elements from the binary symbols at the channel rate; and a selector operably coupled to the other syntax assembler, said selector for selecting context table entries for decoding a portion of the binary symbols on the basis of a portion of the syntax elements, the portion of the syntax elements corresponding to another portion of the binary symbols, the another portion of the binary symbols preceding the portion of the binary symbols. 13. The decoder of another memory operably coupled to the arithmetic decoder, said another memory storing the binary symbols generated by the arithmetic decoder. 14. The decoder of 15. The decoder of Description [0001] This application claims the benefit of “Video Data Processing”, Provisional Application for U.S. Patent, Ser. No. 60/480,415, filed Jun. 20, 2003, by Schumann. [0002] [Not Applicable] [0003] [Not Applicable] [0004] Based on established and proposed standards for encoding and decoding video data, such as H.264 (also known as MPEG-4, Part 10, and Advanced Video Coding), encoded digital video data may be broadcast at data rates exceeding 20 MBits per second for high definition television (HDTV). For compression, the H.264 standard allows individual frames to be encoded using varying amounts of data. As an example, the first frame of a sequence contains complete picture detail, and therefore requires more data, while subsequent frames are largely predicted from preceding frames, and therefore need only enough data to describe the differences. [0005] H.264 optionally uses context adaptive binary arithmetic coding (CABAC) to further compress data that has already been compressed using spatial and temporal prediction, transforms, quantization and other techniques. [0006] Unlike the other methods, CABAC is categorized as lossless compression because CABAC coding does not result in the loss of information. Nevertheless, CABAC can result in considerable compression gains. [0007] In CABAC encoded data, a “syntax element”, which typically represents a coefficient or other datum from prior compression, is encoded as a variable length sequence of binary bits (“Bins”), and the individual Bins (i.e. 2-valued symbols) are then encoded using arithmetic coding. Arithmetic encoding expresses a sequence of symbols as a single fractional binary number between 0 and 1 using recursive subdivision of intervals to encode successive symbols. The number has as many fractional bits of precision as are needed to express its value. The relative likelihood of occurrence of a 1 and a 0 is used to encode the Bin with statistically optimal efficiency. In the CABAC decoder, a dynamic context table is kept with likelihood entries for each of many different types of Bins within syntax elements. The context table is preloaded at the beginning of a “slice” of video data, and subsequently the appropriate context table entry is updated after each Bin of a syntax element is decoded. Because a context table entry is referenced and updated in order for each Bin, parallelization of the decoding process is computationally complex. [0008] A typical HDTV video decoder may assemble 30 frames per second. The standard allows for encoded frame data sizes as high as 12 Mbits per frame for HDTV. Therefore, an arithmetic decoder may need to decode at speeds of 360 Mbits/sec of encoded data at a peak decoding rate, if it is to complete the decoding process for each frame within one frame time. The peak rate of Bins is even higher than 360 Mbits/sec in this case. It is difficult using conventional CMOS integrated circuits, to build an arithmetic decoder and context memory that operates at this rate. [0009] Further limitations and disadvantages of conventional and traditional approaches will become apparent to one of ordinary skill in the art through comparison of such systems with the present invention as set forth in the remainder of the present application with reference to the drawings. [0010] Presented herein is a system and apparatus for accelerating arithmetic decoding of encoded data. [0011] In one embodiment, there is presented a method for decoding context adaptive binary arithmetic coded data. The method comprises receiving a bitstream comprising the context adaptive binary arithmetic coded data at a channel rate; decoding the context adaptive binary arithmetic coded data at the channel rate, wherein decoding the context adaptive binary arithmetic coded data at the channel rate comprises generating a stream of intermediate binary symbols from the context adaptive binary arithmetic coded data at the channel rate; and decoding the stream of intermediate binary symbols at a consumption rate. [0012] In another embodiment, there is presented a symbol interpreter for decoding context adaptive binary arithmetic coded data. The symbol interpreter comprises a first memory, a context adaptive binary arithmetic coded data decoding loop, and a syntax assembler. The first memory receives a bitstream comprising the context adaptive binary arithmetic coded data at a channel rate. The context adaptive binary arithmetic coded data decoding loop decodes the context adaptive binary arithmetic coded data at the channel rate, and comprises an arithmetic decoder for generating intermediate binary symbols from the context adaptive binary arithmetic coded data at the channel rate. The syntax assembler decodes the intermediate binary symbols to generate syntax elements at a consumption rate. [0013] In another embodiment, there is presented a decoder for decoding context adaptive binary arithmetic coded data. The decoder comprises a first memory, a context adaptive binary arithmetic coded data decoding loop, and a syntax assembler. The first memory receives a bitstream comprising the context adaptive binary arithmetic coded data at a channel rate. The context adaptive binary arithmetic coded data decoding loop is operably coupled to the first memory to decode the context adaptive binary arithmetic coded data at the channel rate, and comprises an arithmetic decoder. The arithmetic decoder is operably coupled to the first memory to generate intermediate binary symbols from the context adaptive binary arithmetic coded data at the channel rate. The syntax assembler is operably coupled to the arithmetic decoder to decode the binary symbols to generate syntax elements at a consumption rate. [0014] These and other advantages, aspects and novel features of the present invention, as well as details of illustrative aspects thereof, will be more fully understood from the following description and drawings. [0015]FIG. 1 is a block diagram describing exemplary encoded data; [0016]FIG. 2 is a block diagram of a video decoder in accordance with an embodiment of the present invention; [0017]FIG. 3 is a block diagram of an exemplary context adaptive binary arithmetic code decoder in accordance with an embodiment of the present invention; and [0018]FIG. 4 is a flow diagram for decoding encoded data in accordance with an embodiment of the present invention. [0019] Referring now to FIG. 1, there is illustrated a block diagram describing exemplary encoded data. A data stream, that can represent a variety of original data [0020] For example, where the original data is digital video, compression standards such as H.264 use spatial, temporal prediction, transformations, quantization, and scanning to reduce the amount of data representing the video data. Generally, the video data is represented by frequency coefficients and side information, known as syntax elements [0021] A transmitter can then transmit or broadcast the CABAC data [0022] To display the frames for HDTV, the decoder reconstructs frames, on average, at least 30 frames/second. However, in H.264, varying amounts of the CABAC data [0023] Referring now to FIG. 2, there is illustrated a block diagram describing an exemplary video decoder [0024] The symbol interpreter [0025] The symbol interpreter [0026] Referring now to FIG. 3, there is illustrated a block diagram of the symbol interpreter [0027] The CABAC decoding loop decodes the CABAC data [0028] While the CABAC decoding loop decodes the CABAC data [0029] The symbol interpreter [0030] Referring now to FIG. 5, there is illustrated a flow diagram for decoding CABAC data [0031] At [0032] Decoding the CABAC data [0033] The Bins [0034] The embodiments described herein may be implemented as a board level product, as a single chip, application specific integrated circuit (ASIC), as part of an ASIC containing other functions, or with varying levels of the decoder system integrated with other portions of the system as separate components. [0035] The degree of integration of the decoder system will primarily be determined by the speed and cost considerations. Because of the sophisticated nature of modern processor, it is possible to utilize a commercially available processor, which may be implemented external to an ASIC implementation. If the processor is available as an ASIC core or logic block, then the commercially available processor can be implemented as part of an ASIC device wherein certain functions can be implemented in firmware. Alternatively, the functions can be implemented as hardware accelerator units controlled by the processor. [0036] While the present invention has been described with reference to certain embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the scope of the present invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the present invention without departing from its scope. [0037] Therefore, it is intended that the present invention not be limited to the particular embodiment disclosed, but that the present invention will include all embodiments falling within the scope of the appended claims. Referenced by
Classifications
Legal Events
Rotate |